Knowledge catalogue
arXiv:2607.28442v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a ke
arXiv:2510.20535v2 Announce Type: replace Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Co
arXiv:2607.26455v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquir
Google DeepMind says the latest version of its Gemini Robotics AI model can 'control entire humanoid robots.' While the previous model focused on controlling a humanoid robot's upper body, Gemini Robo
arXiv:2607.27201v1 Announce Type: new Abstract: World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and h
arXiv:2607.26448v1 Announce Type: new Abstract: A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length
one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel
arXiv:2607.26196v1 Announce Type: new Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet exis
arXiv:2607.26608v1 Announce Type: new Abstract: Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvem
arXiv:2607.27113v1 Announce Type: new Abstract: The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generat
arXiv:2607.24838v1 Announce Type: cross Abstract: In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs
arXiv:2607.23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment. Existing context co
arXiv:2607.24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynam
arXiv:2607.22721v1 Announce Type: cross Abstract: Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning. For patients
arXiv:2607.22898v1 Announce Type: cross Abstract: Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts
arXiv:2607.23278v1 Announce Type: new Abstract: Multi-hop question answering requires coordinating relational and textual evidence across reasoning steps, a combination neither a text corpus nor a kno
arXiv:2607.24554v1 Announce Type: cross Abstract: Advancing multimodal retrieval-augmented generation (RAG) for complex document understanding presents a formidable dual dilemma of accuracy and effici
arXiv:2607.23132v1 Announce Type: new Abstract: Assessing the severity of a traffic accident scenario is important to decide which emergency service to dispatch. Missing an ambulance dispatch on a ped
arXiv:2607.23442v1 Announce Type: new Abstract: LLM debate is usually evaluated by final answers, but transcripts also reveal whether later turns develop new argumentative content or return to earlier
arXiv:2607.23614v1 Announce Type: cross Abstract: We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories. The verifier evaluates
arXiv:2607.23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.1, can serve as the high-level controller of a physical mobile robot
arXiv:2607.23762v1 Announce Type: cross Abstract: Conventional recommenders capture users' preferences by optimizing observed user-item relations, whereas continuous generative recommendation addition
arXiv:2507.21438v2 Announce Type: replace Abstract: Ontologies and knowledge graphs require continuous evolution to remain comprehensive and accurate, but manual curation is labor intensive. Large Lan
arXiv:2607.24730v1 Announce Type: cross Abstract: Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In cl
arXiv:2607.22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue. Existing medical QA
Mage-VL is a codec-native, proactive-streaming multimodal foundation model for image and video understanding, whose visual encoder is trained entirely from scratch at a compact 4B scale. It targets a
arXiv:2607.22552v1 Announce Type: new Abstract: The automatic translation of mathematical expressions in scientific literature into executable symbolic code (a process we refer to as Formula Formaliza
arXiv:2607.24074v1 Announce Type: new Abstract: We present MiSS, a black-box, query-based framework for explaining 3D point cloud classifiers through perturbation-relative sufficiency reasoning. MiSS
arXiv:2511.23304v2 Announce Type: replace Abstract: In this paper, we propose a novel Multi-Modal Scene Graph with Kolmogorov-Arnold Expert Network for Audio-Visual Question Answering (SHRIKE). The ta
arXiv:2607.23445v1 Announce Type: cross Abstract: Omnimodal large language models (OmniLLMs) are rapidly extending multimodal reasoning to cover synchronized audio and video. However, the resulting au
arXiv:2607.19063v2 Announce Type: replace Abstract: Objective Structured Clinical Examinations (OSCEs) are the gold standard for assessing clinical competence, yet scoring remains vulnerable to examin
arXiv:2607.24447v1 Announce Type: new Abstract: On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories ge
arXiv:2607.24191v1 Announce Type: cross Abstract: Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key l
arXiv:2607.22954v1 Announce Type: new Abstract: Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world d
arXiv:2607.23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations. They offer a fle
arXiv:2601.13731v2 Announce Type: replace-cross Abstract: Symbolic computation, powered by modern computer algebra systems, has important applications in mathematical reasoning through exact deep comp
arXiv:2607.22494v1 Announce Type: cross Abstract: Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are be
arXiv:2606.16794v2 Announce Type: replace Abstract: This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing visual attention explanations in facial skin d
arXiv:2607.22083v1 Announce Type: cross Abstract: We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-
arXiv:2601.12291v2 Announce Type: replace-cross Abstract: Scalable and maintainable maps are fundamental to large-scale navigation and the long-term deployment of robots in real-world environments. Ho
arXiv:2607.22043v1 Announce Type: new Abstract: Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of th
arXiv:2507.01551v3 Announce Type: replace-cross Abstract: Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~
I have been running some experiments with smaller open-weight LLMs on multiple-choice questions of Swedish medical licensing exams. On a dataset called MedQA-SWE, GPT-4 scored 84% accuracy in 2024 and
There are a few reasons why problems from International Mathematical Olympiad function as a good benchmark for LLMs: - The problems are new, not included in the training data of any model - Hard math
arXiv:2607.21291v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost. Existing
arXiv:2606.14502v2 Announce Type: replace Abstract: Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reason
arXiv:2607.20557v1 Announce Type: cross Abstract: Scientific discovery is increasingly shifting from isolated disciplines to multi-domain reasoning, and AI for science faces a similar transition. Exis
arXiv:2607.21183v1 Announce Type: cross Abstract: The propositional abduction problem is a well-known form of non-monotonic reasoning where we are asked to find an explanation of a given manifestation
arXiv:2509.14257v3 Announce Type: replace-cross Abstract: Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically
So, i have been building some apps that should run on the local every user system, tried gemma4 although its fast and great at reasoning its not as good in instructions following and tool calling. tri
arXiv:2510.05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a singl
arXiv:2607.20284v1 Announce Type: new Abstract: The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU
arXiv:2607.19739v1 Announce Type: cross Abstract: Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive wo
arXiv:2607.19450v1 Announce Type: cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool
arXiv:2607.20207v1 Announce Type: new Abstract: Practical robotic grasping in complex scenes requires both 3D spatial reasoning and alignment with task-specific requirements. Vision-language models (V
arXiv:2607.19794v1 Announce Type: new Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners p
My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me f
arXiv:2607.13643v1 Announce Type: cross Abstract: Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language mode
arXiv:2607.13344v1 Announce Type: new Abstract: Constraint Answer Set Programming (CASP) is a hybrid reasoning paradigm that combines Answer Set Programming (ASP) with Constraint Processing and Satisf
arXiv:2607.13394v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encour